RankingKimi-K2.6
Kimi-K2.6
Kimi-K2.6 by Moonshot is a Kimi model. This profile collects the published benchmark results and reported effort settings for this model. Configurations are compared on the effort page. Ranks are on the leaderboard.
69 published benchmark measures · 46 measured effort results · 17 benchmark families contribute across 7 task areas. 4 capability estimates available in the full profile. See all results ↓ · Compare published benchmarks →
Model evidence summary
This profile combines published settings. It is not a runnable configuration or a leaderboard rank. Compare measured configurations →
Performance profile
Capabilities
Filled points are supported; hollow points are preliminary. Lines stop at unknown capabilities. Exact values and sources follow below.
Scores estimate outcomes against a shared reference panel; they are not accuracy percentages. Sparse or disconnected evidence cannot qualify an overall profile. Open a capability to inspect its evidence.
Reported effort · Reasoning + unspecified
Settings reported in this model's published benchmark results, including results outside the aggregate. Effort names are provider-specific. These are not API defaults or equal compute budgets.
- Reasoning: 33 observations
- Not specified: 56 observations
Mixed settings means multiple settings occur in the evidence. Best across efforts means the source selected its best reported result across settings; it does not mean Max. Unspecified settings stay unknown. This model-summary chart combines reported settings. The leaderboard keeps identified configurations separate and excludes unknown effort.
Inspect each result and its source ↓ · Download effort evidenceScore contributions and missing evidence
17 contributing families across 7 capabilities. Fixed reference panels do not change when the catalog expands.
Capability is fitted jointly across families. Capability estimates below describe different task areas; their weighted sum is not the Capability score.
Results without reviewed compatibility or a reference match remain in the raw evidence below. Coverage counts only contributing results.
Model information & shareable badge
- Lab
- Moonshot
- Catalog status
- api-listed
- Availability
- Documented provider API and open weights for self-hosting
- Family
- Kimi
- Released
- —
- Context
- 256,000 tokens
- License
- —
- Model card
- https://huggingface.co/moonshotai/Kimi-K2.6
- Default Capability family coverage
/badge/kimi-k2.6.svg
Kimi-K2.6 measured results by effort setting
Each row is one published result for one effort setting. Evidence collected 2026-11-22. Compare the effort settings →
| Benchmark | Effort | Score | Source |
|---|---|---|---|
| AA-Briefcase Elo | Reasoning | 821 | Artificial Analysis |
| AA-LCR v1.1 | Non-reasoning | 69.7% | Artificial Analysis |
| AA-LCR v1.1 | Reasoning | 81.0% | Artificial Analysis |
| Agents' Last Exam | High | 9.2% | Agents' Last Exam |
| APEX-Agents-AA | Reasoning | 28.5% | Artificial Analysis |
| AutomationBench-AA | Reasoning | 13.0% | Artificial Analysis |
| CritPt | Non-reasoning | 1.4% | Artificial Analysis |
| CritPt | Reasoning | 8.0% | Artificial Analysis |
| EnterpriseOps-Gym-AA | Reasoning | 38.5% | Artificial Analysis |
| Epoch · Chess Puzzles · v2.0.0 | Unspecified | 20.0% | Epoch AI |
| Epoch · FrontierMath Tier 4 · v2.0.0 | Unspecified | 25.6% | Epoch AI |
| Epoch · FrontierMath Tiers 1–3 · v2.0.0 | Unspecified | 57.2% | Epoch AI |
| Epoch · GPQA diamond · v1.0.8 | Unspecified | 90.8% | Epoch AI |
| Epoch · Mystery Game Puzzles · v1.0.4 · Tool submission | Non-reasoning | 12.0% | Epoch AI |
| Epoch · Mystery Game Puzzles · v1.0.4 · Tool submission | Unspecified | 18.0% | Epoch AI |
| Epoch · OTIS Mock AIME 2024-2025 · v1.1.3 | Unspecified | 96.1% | Epoch AI |
| Epoch · SimpleQA Verified · v1.0.0 | Unspecified | 34.9% | Epoch AI |
| GDP.pdf: All-pass Rate | Reasoning | 13.0% | Artificial Analysis |
| GDPval-AA v2.1 Leaderboard | Reasoning | 1046 | Artificial Analysis |
| GPQA Diamond | Non-reasoning | 78.8% | Artificial Analysis |
| GPQA Diamond | Reasoning | 91.1% | Artificial Analysis |
| Humanity's Last Exam | Non-reasoning | 19.6% | Artificial Analysis |
| Humanity's Last Exam | Reasoning | 37.5% | Artificial Analysis |
| IFBench | Non-reasoning | 44.3% | Artificial Analysis |
| IFBench | Reasoning | 76.0% | Artificial Analysis |
| ITBench-AA | Reasoning | 31.2% | Artificial Analysis |
| MLCR-AA | Reasoning | 11.1% | Artificial Analysis |
| MMMU-Pro | Reasoning | 79.4% | Artificial Analysis |
| SciCode | Reasoning | 51.5% | Artificial Analysis |
| Terminal-Bench Hard | Non-reasoning | 37.9% | Artificial Analysis |
| Terminal-Bench Hard | Reasoning | 43.9% | Artificial Analysis |
| Terminal-Bench v2.1 | Reasoning | 65.9% | Artificial Analysis |
| Terminal-Bench v4.0 | Reasoning | 0.5% | Artificial Analysis |
| ThinkingBox-Bench | Unspecified | 37.7% | Microsoft and Hugging Face |
| Toolathlon-Verified | Unspecified | 58.0% | HKUST NLP |
| Vals AI · Code Migration v1 | Unspecified | 27.8% | Vals AI |
| Vals AI · Excel Modeling Benchmark v1 | Unspecified | 57.9% | Vals AI |
| Vals AI · Finance Agent v2 | Unspecified | 44.9% | Vals AI |
| Vals AI · Legal Research Bench v1 | Unspecified | 15.9% | Vals AI |
| Vals AI · MMLU-Pro v1 | Unspecified | 87.6% | Vals AI |
| Vals AI · Tax Agent Bench v1: Weighted Pass | Unspecified | 45.1% | Vals AI |
| Vals AI · Terminal-Bench 2.1 | Unspecified | 53.6% | Vals AI |
| Vals AI · Vibe Code Bench v1.1 | Unspecified | 37.9% | Vals AI |
| 𝜏²-Bench Telecom | Non-reasoning | 93.9% | Artificial Analysis |
| 𝜏²-Bench Telecom | Reasoning | 95.9% | Artificial Analysis |
| 𝜏³-Banking | Reasoning | 23.3% | Artificial Analysis |
Benchmark scores & sources
Original results, evaluation harnesses, and evidence behind this model.
| Benchmark | Bucket | Score | Harness | Evidence | Source-recorded date |
|---|---|---|---|---|---|
| AA-LCR · source release snapshot; version not specified | Long context | 70.2%Reported settings & sourceNVIDIA evaluation harness/settings per benchmark in model card; comparator scores are NVIDIA-reported under that protocol. First-party reported result. Original cell: 70.2 nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · Performance table: AA-LCR · reviewed 2026-09-06 | Published configurationcontributes to capability | lab self-report | Reviewed 2026-09-06 |
| Agents' Last Exam | Supporting evidence | 9.2% | Agents' Last Exam · OpenClaw | official board | 2026-10-20 |
| AIME 2026 | Hard reasoning | 96.4%Reported settings & sourceKimi K2.6 card, AIME 2026. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Reasoning: 98304 generation tokens; HLE full set. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, AIME 2026, column 2 · reviewed 2026-11-22 | Published configuration | lab self-report | Reviewed 2026-11-22 |
| AIME 2026 · source release snapshot; version not specified | Hard reasoning | 96.4%Reported settings & sourceMAI avg 4 runs, temperature 1, top-p .97; simple ReAct bash/string-replace; Terminal-Bench ignores predefined timeouts. Comparator configurations from cited reports. First-party reported result; comparator results retain the source evaluation setup. MAI-Thinking-1 technical report · Table 11, PDF page 53 · reviewed 2026-09-06 | Published configurationcontributes to capability | lab self-report | Reviewed 2026-09-06 |
| APEX-Agents | Agentic | 27.9%Reported settings & sourceKimi K2.6 card, APEX-Agents. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, APEX-Agents, column 2 · reviewed 2026-11-22 | Published configuration | lab self-report | Reviewed 2026-11-22 |
| Apex-Shortlist (no tools) · source release snapshot; version not specified | Supporting evidence | 77.4%Reported settings & sourceNVIDIA evaluation harness/settings per benchmark in model card; comparator scores are NVIDIA-reported under that protocol. First-party reported result. Original cell: 77.4 nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · Performance table: Apex-Shortlist (no tools) · reviewed 2026-09-06 | Published configuration | lab self-report | Reviewed 2026-09-06 |
| Apex-Shortlist (with tools) · source release snapshot; version not specified | Supporting evidence | 73.2%Reported settings & sourceNVIDIA evaluation harness/settings per benchmark in model card; comparator scores are NVIDIA-reported under that protocol. First-party reported result. Original cell: 73.2 nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · Performance table: Apex-Shortlist (with tools) · reviewed 2026-09-06 | Published configuration | lab self-report | Reviewed 2026-09-06 |
| BabyVision | Supporting evidence | 39.8%Reported settings & sourceKimi K2.6 card, BabyVision. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Vision: 98304 tokens, average of three runs; Python condition uses 65536 tokens per step, at most50steps. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, BabyVision, column 2 · reviewed 2026-11-22 | Published configuration | lab self-report | Reviewed 2026-11-22 |
| BabyVision (w/ python) | Supporting evidence | 68.5%Reported settings & sourceKimi K2.6 card, BabyVision (w/ python). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Vision: 98304 tokens, average of three runs; Python condition uses 65536 tokens per step, at most50steps. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, BabyVision (w/ python), column 2 · reviewed 2026-11-22 | Published configuration | lab self-report | Reviewed 2026-11-22 |
| BrowseComp | Agentic | 83.2%Reported settings & sourceKimi K2.6 card, BrowseComp. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, BrowseComp, column 2 · reviewed 2026-11-22 | Published configuration | lab self-report | Reviewed 2026-11-22 |
| BrowseComp · source release snapshot; version not specified | Agentic | 83.2%Reported settings & sourceMiniMax launch figure methodology. SWE internal ClaudeCode 4 runs; Terminal 8CPU16GB2h128k Terminus2; Paper/PostTrain Ralph-loop12h; GDPval internal rubric grader; BrowseComp discard64k; OSWorld361tasks. Comparator provider/leaderboard scores where footnoted. First-party reported result; comparator results retain the source evaluation setup. MiniMax M3 model card benchmark figure · figures/benchmark.jpeg · reviewed 2026-09-06 | Published configurationcontributes to capability | lab self-report | Reviewed 2026-09-06 |
| BrowseComp · source release snapshot; version not specified | Agentic | 61.3%Reported settings & sourceNVIDIA evaluation harness/settings per benchmark in model card; comparator scores are NVIDIA-reported under that protocol. First-party reported result. Original cell: 61.3 nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · Performance table: BrowseComp · reviewed 2026-09-06 | Published configurationcontributes to capability | lab self-report | Reviewed 2026-09-06 |
| BrowseComp (Agent Swarm) | Agentic | 86.3%Reported settings & sourceKimi K2.6 card, BrowseComp (Agent Swarm). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Comparison limit: Agent swarm execution is not an individual model configuration. Kimi K2.6 official model card · Evaluation Results table, BrowseComp (Agent Swarm), column 2 · reviewed 2026-11-22 | Published configuration | lab self-report | Reviewed 2026-11-22 |
| CharXiv (RQ) | Multimodal | 80.4%Reported settings & sourceKimi K2.6 card, CharXiv (RQ). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Vision: 98304 tokens, average of three runs; Python condition uses 65536 tokens per step, at most50steps. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, CharXiv (RQ), column 2 · reviewed 2026-11-22 | Published configurationcontributes to capability | lab self-report | Reviewed 2026-11-22 |
| CharXiv (RQ) (w/ python) | Supporting evidence | 86.7%Reported settings & sourceKimi K2.6 card, CharXiv (RQ) (w/ python). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Vision: 98304 tokens, average of three runs; Python condition uses 65536 tokens per step, at most50steps. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, CharXiv (RQ) (w/ python), column 2 · reviewed 2026-11-22 | Published configuration | lab self-report | Reviewed 2026-11-22 |
| Claw Eval (pass@3) | Supporting evidence | 80.9%Reported settings & sourceKimi K2.6 card, Claw Eval (pass@3). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, Claw Eval (pass@3), column 2 · reviewed 2026-11-22 | Published configuration | lab self-report | Reviewed 2026-11-22 |
| Claw Eval (pass^3) | Supporting evidence | 62.3%Reported settings & sourceKimi K2.6 card, Claw Eval (pass^3). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, Claw Eval (pass^3), column 2 · reviewed 2026-11-22 | Published configuration | lab self-report | Reviewed 2026-11-22 |
| Claw-Eval · source release snapshot; version not specified | Supporting evidence | 61.5%Reported settings & sourceMiniMax launch figure methodology. SWE internal ClaudeCode 4 runs; Terminal 8CPU16GB2h128k Terminus2; Paper/PostTrain Ralph-loop12h; GDPval internal rubric grader; BrowseComp discard64k; OSWorld361tasks. Comparator provider/leaderboard scores where footnoted. First-party reported result; comparator results retain the source evaluation setup. MiniMax M3 model card benchmark figure · figures/benchmark.jpeg · reviewed 2026-09-06 | Published configuration | lab self-report | Reviewed 2026-09-06 |
| CritPt (no tools) · source release snapshot; version not specified | Supporting evidence | 9.1%Reported settings & sourceNVIDIA evaluation harness/settings per benchmark in model card; comparator scores are NVIDIA-reported under that protocol. First-party reported result. Original cell: 9.1 nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · Performance table: CritPt (no tools) · reviewed 2026-09-06 | Published configuration | lab self-report | Reviewed 2026-09-06 |
| DeepSearchQA (accuracy) | Supporting evidence | 83%Reported settings & sourceKimi K2.6 card, DeepSearchQA (accuracy). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, DeepSearchQA (accuracy), column 2 · reviewed 2026-11-22 | Published configuration | lab self-report | Reviewed 2026-11-22 |
| DeepSearchQA (f1-score) | Supporting evidence | 92.5%Reported settings & sourceKimi K2.6 card, DeepSearchQA (f1-score). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, DeepSearchQA (f1-score), column 2 · reviewed 2026-11-22 | Published configuration | lab self-report | Reviewed 2026-11-22 |
| GDPVal · source release snapshot; version not specified | Agentic | 50.4%Reported settings & sourceNVIDIA evaluation harness/settings per benchmark in model card; comparator scores are NVIDIA-reported under that protocol. First-party reported result. Original cell: 50.4 nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · Performance table: GDPVal · reviewed 2026-09-06 | Published configurationcontributes to capability | lab self-report | Reviewed 2026-09-06 |
| GDPval rubrics · source release snapshot; version not specified | Agentic | 65.1%Reported settings & sourceMiniMax launch figure methodology. SWE internal ClaudeCode 4 runs; Terminal 8CPU16GB2h128k Terminus2; Paper/PostTrain Ralph-loop12h; GDPval internal rubric grader; BrowseComp discard64k; OSWorld361tasks. Comparator provider/leaderboard scores where footnoted. First-party reported result; comparator results retain the source evaluation setup. MiniMax M3 model card benchmark figure · figures/benchmark.jpeg · reviewed 2026-09-06 | Published configurationcontributes to capability | lab self-report | Reviewed 2026-09-06 |
| GPQA (no tools) · source release snapshot; version not specified | Hard reasoning | 91%Reported settings & sourceNVIDIA evaluation harness/settings per benchmark in model card; comparator scores are NVIDIA-reported under that protocol. First-party reported result. Original cell: 91.0 nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · Performance table: GPQA (no tools) · reviewed 2026-09-06 | Published configurationcontributes to capability | lab self-report | Reviewed 2026-09-06 |
| GPQA Diamond · source release snapshot; version not specified | Hard reasoning | 90.5%Reported settings & sourceMAI avg 4 runs, temperature 1, top-p .97; simple ReAct bash/string-replace; Terminal-Bench ignores predefined timeouts. Comparator configurations from cited reports. First-party reported result; comparator results retain the source evaluation setup. MAI-Thinking-1 technical report · Table 11, PDF page 53 · reviewed 2026-09-06 | Published configurationcontributes to capability | lab self-report | Reviewed 2026-09-06 |